New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

robustness for Markovized strict labeling #2

Open

kilian-gebhardt opened this issue May 10, 2019 · 0 comments

Owner

kilian-gebhardt commented May 10, 2019

Early experiments for hybrid grammars with Markovized strict labeling show

a reduced number of parse failures compared with strict labeling
still a higher number of parse failures than child labeling

Some fallback mechanism to improve robustness should help.

one could run a different grammar as in the CL article (basically, a fine to coarse pipeline)
can the labeling be adjusted with a similar effect?

kilian-gebhardt added a commit that referenced this issue


          script to simulate fallback strategies for failures #2

45eb4a1

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment